Impedance Based Temperature Estimation of Lithium Ion Cells Using Artificial Neural Networks

• Published in: Batteries (Basel) 2021-12, Vol.7 (4), p.85
• Main Authors: Ströbel, Marco, Pross-Brakhage, Julia, Kopp, Mike, Birke, Kai Peter
• Format: Article
• Language: English
• Subjects: Algorithms; artificial intelligence; artificial neural network; Artificial neural networks; Datasets; Electric cells; Electric vehicles; Electrochemical impedance spectroscopy; Estimation; High temperature; Lithium; Lithium-ion batteries; Methods; Neural networks; Parameterization; Partial differential equations; Product safety; sensorless temperature measurement; Sensors; Spectrum analysis; temperature estimation; Temperature sensors; Time series
• ISSN: 2313-0105; 2313-0105
• DOI: 10.3390/batteries7040085

Tracking the cell temperature is critical for battery safety and cell durability. It is not feasible to equip every cell with a temperature sensor in large battery systems such as those in electric vehicles. Apart from this, temperature sensors are usually mounted on the cell surface and do not detect the core temperature, which can mean detecting an offset due to the temperature gradient. Many sensorless methods require great computational effort for solving partial differential equations or require error-prone parameterization. This paper presents a sensorless temperature estimation method for lithium ion cells using data from electrochemical impedance spectroscopy in combination with artificial neural networks (ANNs). By training an ANN with data of 28 cells and estimating the cell temperatures of eight more cells of the same cell type, the neural network (a simple feed forward ANN with only one hidden layer) was able to achieve an estimation accuracy of ΔT= 1 K (10 ∘C